Using the quantization error from Self-Organized Map (SOM) output for detecting critical variability in large bodies of image time series in less than a minute
This provides a fast detection method for critical changes in image homogeneity, such as in medical or satellite imaging, but appears incremental as it applies an existing method to new data.
The paper tackled the problem of detecting critical variability in large image time series by using the quantization error from Self-Organized Maps, proving it as a reliable indicator with a linear increase in error correlating to variability in spatial contrast.
The quantization error (QE) from SOM applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images, is proven a reliable indicator of potentially critical changes in image homogeneity. The QE is shown to increase linearly with the variability in spatial contrast contents across time when contrast intensity is kept constant.